© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    X is Y pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ¢æĺ¯
    -0.21
    æĹ¢è¦ģ
    -0.21
    æĹ¢èĥ½
    -0.20
    ç»Ħç»ĩçĶŁæ´»
    -0.19
    ä»ķäºĭãĤĴ
    -0.18
    ä¸įä»ħè¦ģ
    -0.17
    èĢĮä¸įæĺ¯
    -0.17
    _rp
    -0.17
    æĹ¢åı¯ä»¥
    -0.17
    daq
    -0.17
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.34
    åĪ«çļĦ
    0.27
    åħ¶ä»ĸ
    0.26
    åħ¶å®ĥ
    0.25
     other
    0.23
    çĶ¬
    0.22
    æľ¬ç½ij
    0.21
     others
    0.20
    åħ¶å®ĥéĹ®é¢ĺ
    0.20
    mund
    0.19
    Activations Density 0.051%

    No Known Activations